{"id":"W1581639473","doi":"10.1007/s10664-012-9209-9","title":"Automated topic naming","year":2012,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; University of British Columbia; University of Alberta","funders":"","keywords":"Computer science; Latent Dirichlet allocation; Topic model; Commit; Categorization; Software; Context (archaeology); Information retrieval; Domain (mathematical analysis); Artificial intelligence; Natural language processing; Data science; Database; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000376458,0.0002270616,0.0002087979,0.0002078144,0.00008223888,0.0001156211,0.0007678248,0.0001230296,0.0000321825],"category_scores_gemma":[0.002564697,0.0002254422,0.0000881036,0.0008306269,0.00001475646,0.0007364163,0.0003918342,0.0003568355,0.0002588585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001838102,"about_ca_system_score_gemma":0.00003576255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006412348,"about_ca_topic_score_gemma":1.244787e-7,"domain_scores_codex":[0.9980299,0.00002675009,0.0002381158,0.0003094691,0.0004546416,0.0009410584],"domain_scores_gemma":[0.9978342,0.00110423,0.00002620547,0.0005806769,0.00005090353,0.000403751],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001694712,0.0001079951,0.9736634,0.000111261,0.00005558391,0.00004167399,0.0009761376,0.01111634,0.0004788493,0.0008807895,0.005817388,0.006748844],"study_design_scores_gemma":[0.0002634517,0.00003973896,0.841128,0.00005241365,0.000005549133,0.00007661543,0.00000417658,0.1164792,0.001447202,0.00002306078,0.0399087,0.0005718668],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2284016,0.0005390106,0.7618927,0.0001515534,0.001035222,0.0001034417,8.638636e-7,0.007840191,0.00003541306],"genre_scores_gemma":[0.858224,0.00000325243,0.1411579,0.0001101388,0.0003199229,0.00003233766,0.000002609097,0.00003676363,0.0001130238],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6298224,"threshold_uncertainty_score":0.9193267,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0256654668367926,"score_gpt":0.2953701151461752,"score_spread":0.2697046483093826,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}